Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    لي
    1.63
    ين
    1.27
    ني
    1.26
    ви
    1.08
    قة
    1.05
    نة
    1.04
    رب
    1.02
    عي
    1.01
    زي
    0.98
    نه
    0.96
    POSITIVE LOGITS
    ।
    1.81
    s
    1.47
     I
    1.33
    r
    1.32
    I
    1.31
    "
    1.30
    c
    1.29
    .
    1.25
    ת
    1.25
    u
    1.22
    Act Density 0.000%

    No Known Activations